Metraipolis › archive › dc_57ecbe4f8a98

Component-Level Evaluation of Adaptive PINN Training for CFD-Oriented Crystal Growth Simulation — arXiv:2610.05127

Source
arXiv
Original
https://arxiv.org/abs/2610.05127
License (as archived)
CC0-1.0
Archived
2026-10-06T05:30:55.371Z
SHA-256 of the archived text
83c93fc49a6f1d882d14cd9f4df35a62450e5d6c54a25759fa035a947056ffe7
Stable URL of this page
https://metraipolis.com/documento/dc_57ecbe4f8a98

How to cite

Component-Level Evaluation of Adaptive PINN Training for CFD-Oriented Crystal Growth Simulation — arXiv:2610.05127 — arXiv, https://arxiv.org/abs/2610.05127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57ecbe4f8a98 (Metraipolis archive dc_57ecbe4f8a98, sha256 83c93fc49a6f1d882d14cd9f4df35a62450e5d6c54a25759fa035a947056ffe7)
BibTeX
@misc{dc57ecbe4f8a98,
  title = {Component-Level Evaluation of Adaptive PINN Training for CFD-Oriented Crystal Growth Simulation — arXiv:2610.05127},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05127},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57ecbe4f8a98; sha256 83c93fc49a6f1d882d14cd9f4df35a62450e5d6c54a25759fa035a947056ffe7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physics-informed neural network (PINN) training minimizes a weighted combination of partial differential equation (PDE), boundary-condition, and initial-condition losses. Because adaptive methods modify these weights during training, their weighted total losses are not always directly comparable. We compare fixed-weight PINN, gradient-normalized PINN (GNPINN), and a rule-based adaptive controller (AgenticPINN) under matched settings on a heat-equation benchmark and a simplified Czochralski-oriented thermal-fluid problem. In the crystal-growth MLP experiment, adaptive control reduced the PDE residual from the order of $10^{-5}$ to $10^{-6}$, while the boundary-condition loss increased from the order of $10^{-5}$ to $10^{-2}$. On the heat-equation benchmark, GNPINN achieved the lowest relative $L_2$ field error (0.054), whereas AgenticPINN obtained the smallest PDE residual but a relative $L_2$ error of 1.368. Gaussian-process surrogates were additionally evaluated using case-wise holdout tests on corrected Czochralski CFD parameter sweeps. The temperature-field error for the temperature sweep was approximately 6%, whereas the axial-velocity error for the crystal-rotation sweep was approximately 42%. These findings show that adaptive control can improve equation satisfaction while weakening other physical constraints. PINN training should therefore be evaluated using separate PDE, boundary-condition, and solution-error metrics rather than weighted total loss alone.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05127 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:27:05.767Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).